Oxbotica, the autonomous vehicle technology company, is using deepfake technology to help improve autonomous vehicle safety in different weather conditions.
Deepfake technology has been made famous for being used to mimic actors and politicians in viral videos online, but the same technology can be used to generate photo-realistic images to help mitigate adverse conditions or rare on-road events, making its autonomous vehicles (AVs) safer.
Paul Newman, co-founder and chief technology officer at Oxbotica, said: “Using deepfakes is an incredible opportunity for us to increase the speed and efficiency of safely bringing autonomy to any vehicle in any environment – a central focus of our Universal Autonomy vision.
“What we’re really doing here is training our AI to produce a syllabus for other AIs to learn from. It’s the equivalent of giving someone a fishing rod rather than a fish. It offers remarkable scaling opportunities.”
Newman said that while there is no substitute for real-world testing, the autonomous vehicle industry has become concerned with the number of miles travelled as a synonym for safety.
However, the use of deepfakes can help to test countless scenarios. This will allow Oxbotica to scale its real-world testing “exponentially”.
The data is generated by an advanced teaching cycle made up of two co-evolving AIs, one is attempting to create ever more convincing fake images while the other tries to detect which are real and which have been reproduced.
Oxbotica engineers have designed a feedback mechanism which sees both entities improve over time in a bid to outsmart their adversary.
Over time, the detection mechanism will become unable to spot the difference, which means the deepfake AI module is ready to be used to generate data to teach other AIs.
The benefit of which is not in eliminating real experiences but rather augmenting them in a way which scales arbitrarily faster than time or human resource.
At any one time, Oxbotica is able to generate the experiences of any number of vehicles in any number of settings, taking into account different lighting or weather conditions.